© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2753
    Prev
    Next
    INDEX
    Explanations

    latex document class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     program
    0.39
    program
    0.37
     Bites
    0.35
    目录
    0.35
     Maced
    0.34
     Planes
    0.34
     Manners
    0.34
    虚
    0.34
     deep
    0.33
     tout
    0.33
    POSITIVE LOGITS
    ಪೆ
    0.38
    cki
    0.36
    ➷
    0.36
    yata
    0.35
     asociada
    0.34
    expat
    0.34
     Oviedo
    0.33
    preventDefault
    0.33
     करू
    0.33
     pouv
    0.33
    Activations Density 0.001%

    No Known Activations